mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Frederic Weisbecker <fweisbec@gmail.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Paul Mackerras <paulus@samba.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	"K. Prasad" <prasad@linux.vnet.ibm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: [PATCH 7/9] x86/perf: Exclude the debug stack from the callchains
Date: Sun,  6 Dec 2009 08:34:56 +0100	[thread overview]
Message-ID: <1260084898-11686-8-git-send-regression-fweisbec@gmail.com> (raw)
In-Reply-To: <1260084898-11686-1-git-send-regression-fweisbec@gmail.com>

Dumping the callchains from breakpoint events with perf gives strange
results:

3.75%             perf  [kernel]           [k] _raw_read_unlock
                       |
                       --- _raw_read_unlock
                           perf_callchain
                           perf_prepare_sample
                           __perf_event_overflow
                           perf_swevent_overflow
                           perf_swevent_add
                           perf_bp_event
                           hw_breakpoint_exceptions_notify
                           notifier_call_chain
                           __atomic_notifier_call_chain
                           atomic_notifier_call_chain
                           notify_die
                           do_debug
                           debug
                           munmap

We are infected with all the debug stack. Like the nmi stack, the debug
stack is undesired as it is part of the profiling path, not helpful for
the user.

Ignore it.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
---
 arch/x86/kernel/cpu/perf_event.c |    9 +++++----
 1 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c1bbed1..d35f260 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2287,7 +2287,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
-static DEFINE_PER_CPU(int, in_nmi_frame);
+static DEFINE_PER_CPU(int, in_ignored_frame);
 
 
 static void
@@ -2303,8 +2303,9 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-	per_cpu(in_nmi_frame, smp_processor_id()) =
-			x86_is_stack_id(NMI_STACK, name);
+	per_cpu(in_ignored_frame, smp_processor_id()) =
+			x86_is_stack_id(NMI_STACK, name) ||
+			x86_is_stack_id(DEBUG_STACK, name);
 
 	return 0;
 }
@@ -2313,7 +2314,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	if (per_cpu(in_nmi_frame, smp_processor_id()))
+	if (per_cpu(in_ignored_frame, smp_processor_id()))
 		return;
 
 	if (reliable)
-- 
1.6.2.3


  parent reply	other threads:[~2009-12-06  7:35 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-06  7:34 [GIT PULL] perf/hw-breakpoints: Various updates Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 1/9] hw-breakpoints: Add two reserved fields for future extensions Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 2/9] perf: Remove pointless union that wraps the hw breakpoint fields Frederic Weisbecker
2009-12-06 10:38   ` Peter Zijlstra
2009-12-07  1:46     ` Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 3/9] perf: Remove unused struct perf_event::event_callback Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 4/9] hw-breakpoints: Drop callback and task parameters from modify helper Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 5/9] hw-breakpoints: Use overflow handler instead of the event callback Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 6/9] perf: Remove the "event" callback from perf events Frederic Weisbecker
2009-12-06 10:40   ` Peter Zijlstra
2009-12-06  7:34 ` Frederic Weisbecker [this message]
2009-12-06  7:34 ` [PATCH 8/9] x86: Fixup wrong debug exception frame link in stacktraces Frederic Weisbecker
2009-12-06  7:34 ` [PATCH 9/9] x86: Fixup wrong irq " Frederic Weisbecker
2009-12-06  7:58 ` [GIT PULL] perf/hw-breakpoints: Various updates Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1260084898-11686-8-git-send-regression-fweisbec@gmail.com \
    --to=fweisbec@gmail.com \
    --cc=acme@redhat.com \
    --cc=benh@kernel.crashing.org \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=prasad@linux.vnet.ibm.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome